cs.CRNov 1, 2026

Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security

Authors: Shiyu Kan, Yue Qi, Yufei Han, Xinjian Luo, Guojun Xiong, Xiaofeng Gao

Organizations: Shanghai Jiao Tong University, Shanghai, China · Inria, Rennes, France

Abstract

Large language model based agents increasingly rely on external tools to invoke services and interact with web resources. These tools can evolve through software updates, yet agentic frameworks may continue trusting them without re-verifying their safety after implementation changes. This tool update gap creates a supply-chain vulnerability in agentic systems: because updated tool code executes outside the LLM's context window, malicious functionality embedded in tool updates can bypass defenses centered on model-visible interactions, leaving agents exposed to stealthy, persistent threats that existing in-context defenses can hardly address. To thoroughly investigate this threat, we introduce ETUDE (Exploiting Tool Updates for Direct Execution), an attack that embeds malicious functionality into updates of initially benign tools to produce compromised tools, while preserving their legitimate tool functionality. Unlike prompt-based attacks, ETUDE operates entirely outside the LLM's context and requires no adversarial instructions, thereby bypassing defenses restricted to model-visible content. We evaluate ETUDE across three representative attack workloads and seven widely used commercial and open-source agentic frameworks, including Gemini CLI, Codex CLI, and Claude Code. The results show that ETUDE achieves a 97.6% ASR while maintaining a 95.9% legitimate task completion rate. We further examine existing defenses and find that they provide insufficient protection against this threat. These findings expose a fundamental blind spot in current agent security practices: trust established for a tool does not necessarily remain valid after its implementation updates.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback

    May 17, 2026Lecheng Yan, Ruizhe Li, Xicheng Han +5AI Agent ReliabilityLLM Agent Evaluation

  2. AgenTRIM: Tool Risk Mitigation for Agentic AI

    Jan 18, 2026Roy Betser, Amit Giloni, Shamik Bose +4LLM Agent SecurityIndirect Prompt Injection